Hybrid Phishing Detecting with Recommendation Decision Trees

Abstract

Phishing is performed by trying to trick the victim into accessing any computing information that looks original and then instructing them to send important data to unrestricted/unwanted private resources. For prevention, it is essential to develop a phishing detection system. Recent phishing detection systems are based on data mining and machine learning techniques. Most of the related work literature requires the collection of previous phishing attack logs, analyzing them creating a list of such activities, and blocking traffic from such sources. However, this is a cumbersome task because the data size is very large, continues changing, and is dynamic in nature. [1]. Instead of using a single algorithm approach, it would be better to use a hybrid approach. A hybrid approach would be better at mitigating phishing attacks because the classification of different formats of data is handled; whether the intruder wants to use images or textural input to gain into another user system for phishing. Hybrid recommendation decision trees enhance any of the machine learning and deep learning algorithms' performance. The decision path of the model followed a series of if/else/then statements that connect the predicted class from the root of the tree through the branches of the tree to detect true positives and false negatives of phishing attempts. 10 decision trees were considered and used the features to train the recommendation decision regression model. The developed hybrid recommendation decision tree approach provided an overall true positive rate of the model of 92.28 % and a false negative rate is 7.4%.